Best Practices of Using AI-Based Models in Crystallography and Their Impact in Structural Biology
Journal of Chemical Information and Modeling · 26.06.2023 · 63 (12) · 3637-3646
DOI: 10.1021/acs.jcim.3c00381 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 12.06.2023. Verfasst von Marc Graille und 2 weiteren Autor:innen. Beteiligte Einrichtung: Laboratoire de Biologie Structurale de la Cellule (BIOC), CNRS, École Polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France. Hauptthemen laut MEDLINE: Artificial Intelligence, Software. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 119 Literaturangaben. Gefördert von: Agence Nationale de la Recherche, ?cole Polytechnique, Universit? Paris-Saclay, Centre National de la Recherche Scientifique.
Abstract (Originalsprache)
The recent breakthrough made in the field of three-dimensional (3D) structure prediction by artificial intelligence softwares, such as initially AlphaFold2 (AF2) and RosettaFold (RF) and more recently large Language Models (LLM), has revolutionized the field of structural biology in particular and also biology as a whole. These models have clearly generated great enthusiasm within the scientific community, and different applications of these 3D predictions are regularly described in scientific articles, demonstrating the impact of these high-quality models. Despite the acknowledged high accuracy of these models in general, it seems important to make users of these models aware of the wealth of information they offer and to encourage them to make the best use of them. Here, we focus on the impact of these models in a specific application by structural biologists using X-ray crystallography. We propose guidelines to prepare models to be used for molecular replacement trials to solve the phase problem. We also encourage colleagues to share as much detail as possible about how they use these models in their research, where the models did not yield correct molecular replacement solutions, and how these predictions fit with their experimental 3D structure. We feel this is important to improve the pipelines using these models and also to get feedback on their overall quality.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Laboratoire de Biologie Structurale de la Cellule (BIOC), CNRS, École Polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France.
- Laboratoire de Biochimie Théorique, CNRS, Université Paris Cité, 75005 Paris, France.
ORCID-Profile: Marc Graille, Sophie Sacquin-Mora, Antoine Taly
Förderung
- Agence Nationale de la Recherche
- ?cole Polytechnique, Universit? Paris-Saclay
- Centre National de la Recherche Scientifique
Zitieren
APA
Graille, M., Sacquin-Mora, S., & Taly, A. (2023). Best Practices of Using AI-Based Models in Crystallography and Their Impact in Structural Biology. Journal of Chemical Information and Modeling, 63(12), 3637-3646. https://doi.org/10.1021/acs.jcim.3c00381
Vancouver
Graille M, Sacquin-Mora S, Taly A. Best Practices of Using AI-Based Models in Crystallography and Their Impact in Structural Biology. Journal of Chemical Information and Modeling. 2023;63(12):3637-3646. doi:10.1021/acs.jcim.3c00381
BibTeX
@article{Graille2023,
author = {Graille, Marc and Sacquin-Mora, Sophie and Taly, Antoine},
title = {Best Practices of Using AI-Based Models in Crystallography and Their Impact in Structural Biology},
journal = {Journal of Chemical Information and Modeling},
year = {2023},
volume = {63},
number = {12},
pages = {3637--3646},
doi = {10.1021/acs.jcim.3c00381}
}
EUVIMED